3D Shape Generation: A Survey

2025-06-27

AI Summary

This paper presents a systematic survey of deep learning–driven 3D shape generation, addressing three core dimensions: shape representation, generative modeling, and evaluation protocols. Methodologically, it introduces the first unified taxonomy covering explicit (e.g., meshes), implicit (e.g., SDFs, NeRFs), and hybrid representations, traces the evolution of feedforward-based generative architectures, and consolidates major benchmarks (e.g., ShapeNet, FAUST) and metrics (e.g., Chamfer distance, Jensen–Shannon divergence), revealing inherent trade-offs among fidelity, diversity, and realism. Its principal contribution is a novel “representation–model–evaluation” triadic analytical framework, which explicitly identifies controllable shape modeling, efficient inference, and physically consistent generation as key open challenges. The framework establishes a structured benchmark and roadmap for future research in 3D generative modeling. (126 words)

Technology Category

Computer Vision: 3D Computer VisionMachine Learning: Deep Generative Models & AutoencodersKnowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

User Modeling, Personalization and Recommendation: User model development and evaluationSearch and Retrieval-Augmented AI: Web evaluation methodologies and metricsGraph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Recent advances in deep learning have significantly transformed the field of 3D shape generation, enabling the synthesis of complex, diverse, and semantically meaningful 3D objects. This survey provides a comprehensive overview of the current state of the art in 3D shape generation, organizing the discussion around three core components: shape representations, generative modeling approaches, and evaluation protocols. We begin by categorizing 3D representations into explicit, implicit, and hybrid setups, highlighting their structural properties, advantages, and limitations. Next, we review a wide range of generation methods, focusing on feedforward architectures. We further summarize commonly used datasets and evaluation metrics that assess fidelity, diversity, and realism of generated shapes. Finally, we identify open challenges and outline future research directions that could drive progress in controllable, efficient, and high-quality 3D shape generation. This survey aims to serve as a valuable reference for researchers and practitioners seeking a structured and in-depth understanding of this rapidly evolving field.

Problem

• Surveying 3D shape generation methods and representations
• Reviewing generative modeling approaches for 3D objects
• Evaluating datasets and metrics for shape fidelity and diversity

Innovation

• Deep learning transforms 3D shape generation
• Survey covers shape representations and methods
• Focus on fidelity, diversity, and realism metrics